Twelve projects in three tiers: the thesis, the satellites around it, and an annex for roots, take-home assessments and size exercises. Filter by the stack you care about.
FILTER BY STACK (44)
12 PROJECTS ON SHOW
Thesis
F32026
CodebaseRAG
Hexagonal RAG over your own codebase, with a deterministic, eval-first core: ingest, query, and CI-gated retrieval evals.
The result is an eval gate that blocks retrieval regressions before merge: quality is a CI-checked claim with a committed floor, not a demo vibe.
Event-driven adapter telemetry: a Kafka gateway + hub pipeline with idempotent Oracle persistence, per-adapter health tracking, alerting, and a live SSE mission-control dashboard.
The result is operational visibility across ~90 adapters in 4 countries: who is DOWN, since when, and exactly one alert per episode — no pager storms, no silent gaps.
A standardized multi-agent harness for Claude Code and OpenCode: Spec-Driven Development roles (Leader, Spec Author, Implementer, Reviewer) installed into any project with a single command. Its process also ships as six standalone skills (npx skills add jordimarsal/harness).
The payoff is repeatable agent work: specs, roles and gates installed in one command, on any stack — this portfolio is built through them.
Voice interview simulator: a local LLM plays the interviewer and Whisper handles transcription, so you can rehearse technical interviews fully offline.
An agentic benchmark for local GGUF models: prompt speed, tool-calling, code generation and multi-step agent work graded under one identical harness, with the raw receipts of every call — 100% local, no cloud, no APIs.
0.85best global score — minicpm-v-4.7-35b-a3b q4_k_m, thinking off